Finding experiments

To use incense we first have to instantiate an experiment loader that will enable us to query the database for specific runs.

QuerySet([Experiment(id=17, name=autoencoder_test), Experiment(id=18, name=autoencoder_test), Experiment(id=19, name=autoencoder_test), Experiment(id=20, name=autoencoder_test), Experiment(id=21, name=autoencoder_test), Experiment(id=22, name=autoencoder_test), Experiment(id=23, name=autoencoder_test), Experiment(id=24, name=autoencoder_test), Experiment(id=74, name=autoencoder_test), Experiment(id=75, name=autoencoder_test)])

pmap({'epochs': 250, 'iteration': False, 'targets_type': 'Mnist', 'batch_size': 256, 'seed': 25619811, 'autoencoder_type': 'Over_dim_iteration'})

	targets_type	iteration	autoencoder_type	batch_size
exp_id
17	Mnist	False	Over_dim_iteration	256
18	Mnist	False	Over_dim_iteration	128
19	Mnist	False	Over_dim_iteration	64
20	Mnist	False	Over_dim_iteration	32
21	10_Targets	False	Over_dim_iteration	256
22	10_Targets	False	Over_dim_iteration	128
23	10_Targets	False	Over_dim_iteration	64
24	10_Targets	False	Over_dim_iteration	32
74	Noisy	False	Over_dim_iteration	256
75	Noisy	False	Over_dim_iteration	128

QuerySet([Experiment(id=17, name=autoencoder_test), Experiment(id=18, name=autoencoder_test), Experiment(id=19, name=autoencoder_test), Experiment(id=20, name=autoencoder_test), Experiment(id=21, name=autoencoder_test), Experiment(id=22, name=autoencoder_test), Experiment(id=23, name=autoencoder_test), Experiment(id=24, name=autoencoder_test), Experiment(id=74, name=autoencoder_test), Experiment(id=75, name=autoencoder_test)])

predictions_df_0

predictions_df_10

predictions_df_20

predictions_df_30

predictions_df_40

predictions_df_50

predictions_df_60

predictions_df_70

predictions_df_80

predictions_df_90

predictions_df_100